public ImageSearchHits search(Document doc, IndexReader reader) throws IOException {
ScalableColor sc = null;
ColorLayout cl = null;
EdgeHistogram eh = null;
String[] cls = doc.getValues(DocumentBuilder.FIELD_NAME_COLORLAYOUT);
if (cls != null && cls.length > 0) {
cl = new ColorLayout();
cl.setStringRepresentation(cls[0]);
}
String[] scs = doc.getValues(DocumentBuilder.FIELD_NAME_SCALABLECOLOR);
if (scs != null && scs.length > 0) {
sc = new ScalableColor();
sc.setStringRepresentation(scs[0]);
}
String[] ehs = doc.getValues(DocumentBuilder.FIELD_NAME_EDGEHISTOGRAM);
if (ehs != null && ehs.length > 0) {
eh = new EdgeHistogram();
eh.setStringRepresentation(ehs[0]);
}
float maxDistance = findSimilar(reader, cl, sc, eh);
return new SimpleImageSearchHits(this.docs, maxDistance);
}
public ImageDuplicates findDuplicates(IndexReader reader) throws IOException {
// get the first document:
if (!IndexReader.indexExists(reader.directory()))
throw new FileNotFoundException("No index found at this specific location.");
Document doc = reader.document(0);
ScalableColor sc = null;
ColorLayout cl = null;
EdgeHistogram eh = null;
String[] cls = doc.getValues(DocumentBuilder.FIELD_NAME_COLORLAYOUT);
if (cls != null && cls.length > 0) {
cl = new ColorLayout();
cl.setStringRepresentation(cls[0]);
}
String[] scs = doc.getValues(DocumentBuilder.FIELD_NAME_SCALABLECOLOR);
if (scs != null && scs.length > 0) {
sc = new ScalableColor();
sc.setStringRepresentation(scs[0]);
}
String[] ehs = doc.getValues(DocumentBuilder.FIELD_NAME_EDGEHISTOGRAM);
if (ehs != null && ehs.length > 0) {
eh = new EdgeHistogram();
eh.setStringRepresentation(ehs[0]);
}
HashMap<Float, List<String>> duplicates = new HashMap<Float, List<String>>();
// find duplicates ...
boolean hasDeletions = reader.hasDeletions();
int docs = reader.numDocs();
int numDuplicates = 0;
for (int i = 0; i < docs; i++) {
if (hasDeletions && reader.isDeleted(i)) {
continue;
}
Document d = reader.document(i);
float distance = getDistance(d, cl, sc, eh);
if (!duplicates.containsKey(distance)) {
duplicates.put(distance, new LinkedList<String>());
} else {
numDuplicates++;
}
duplicates.get(distance).add(d.getField(DocumentBuilder.FIELD_NAME_IDENTIFIER).stringValue());
}
if (numDuplicates == 0) return null;
LinkedList<List<String>> results = new LinkedList<List<String>>();
for (float f : duplicates.keySet()) {
if (duplicates.get(f).size() > 1) {
results.add(duplicates.get(f));
}
}
return new SimpleImageDuplicates(results);
}
/**
* Just opens an image with Java and reports if false if there are problems. This method can be
* used to check for JPG etc. that are not supported by the employed Java version.
*
* @param f the file to check.
* @return true if no exceptions are thrown bey the decoder.
*/
public static boolean isImageFileCompatible(File f) {
boolean result = true;
try {
BufferedImage img = ImageIO.read(f);
ColorLayout cl = new ColorLayout();
cl.extract(img);
} catch (Exception e) {
result = false;
}
return result;
}
private float getDistance(Document d, ColorLayout cl, ScalableColor sc, EdgeHistogram eh) {
float distance = 0f;
int descriptorCount = 0;
if (cl != null) {
String[] cls = d.getValues(DocumentBuilder.FIELD_NAME_COLORLAYOUT);
if (cls != null && cls.length > 0) {
ColorLayout clsi = new ColorLayout();
clsi.setStringRepresentation(cls[0]);
distance += cl.getDistance(clsi) * colorDistributionWeight;
descriptorCount++;
}
}
if (sc != null) {
String[] scs = d.getValues(DocumentBuilder.FIELD_NAME_SCALABLECOLOR);
if (scs != null && scs.length > 0) {
ScalableColor scsi = new ScalableColor();
scsi.setStringRepresentation(scs[0]);
distance += sc.getDistance(scsi) * colorHistogramWeight;
descriptorCount++;
}
}
if (eh != null) {
String[] ehs = d.getValues(DocumentBuilder.FIELD_NAME_EDGEHISTOGRAM);
if (ehs != null && ehs.length > 0) {
EdgeHistogram ehsi = new EdgeHistogram();
ehsi.setStringRepresentation(ehs[0]);
distance += eh.getDistance(ehsi) * textureWeight;
descriptorCount++;
}
}
if (descriptorCount > 0) {
// TODO: find some better scoring mechanism, e.g. some normalization. One thing would be
// linearization of the features!
// For now: Averaging ...
distance = distance / (float) descriptorCount;
}
return distance;
}
public ImageSearchHits search(BufferedImage image, IndexReader reader) throws IOException {
ScalableColor sc = null;
ColorLayout cl = null;
EdgeHistogram eh = null;
if (colorHistogramWeight > 0f) {
sc = new ScalableColor();
sc.extract(image);
}
if (colorDistributionWeight > 0f) {
cl = new ColorLayout();
cl.extract(image);
}
if (textureWeight > 0f) {
eh = new EdgeHistogram();
eh.extract(image);
}
float maxDistance = findSimilar(reader, cl, sc, eh);
return new SimpleImageSearchHits(this.docs, maxDistance);
}